From 261a9e4314d0b7e47cbe05c21508b9311bf48bd4 Mon Sep 17 00:00:00 2001 From: Charan Teja Reddy Date: Thu, 2 Sep 2021 14:59:59 -0700 Subject: [PATCH] BACKPORT: mm: compaction: support triggering of proactive compaction by user The proactive compaction[1] gets triggered for every 500msec and run compaction on the node for COMPACTION_HPAGE_ORDER (usually order-9) pages based on the value set to sysctl.compaction_proactiveness. Triggering the compaction for every 500msec in search of COMPACTION_HPAGE_ORDER pages is not needed for all applications, especially on the embedded system usecases which may have few MB's of RAM. Enabling the proactive compaction in its state will endup in running almost always on such systems. Other side, proactive compaction can still be very much useful for getting a set of higher order pages in some controllable manner(controlled by using the sysctl.compaction_proactiveness). So, on systems where enabling the proactive compaction always may proove not required, can trigger the same from user space on write to its sysctl interface. As an example, say app launcher decide to launch the memory heavy application which can be launched fast if it gets more higher order pages thus launcher can prepare the system in advance by triggering the proactive compaction from userspace. This triggering of proactive compaction is done on a write to sysctl.compaction_proactiveness by user. [1]https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit?id=facdaa917c4d5a376d09d25865f5a863f906234a [akpm@linux-foundation.org: tweak vm.rst, per Mike] Link: https://lkml.kernel.org/r/1627653207-12317-1-git-send-email-charante@codeaurora.org Signed-off-by: Charan Teja Reddy Acked-by: Vlastimil Babka Acked-by: Rafael Aquini Cc: Mike Rapoport Cc: Luis Chamberlain Cc: Kees Cook Cc: Iurii Zaikin Cc: Dave Hansen Cc: Mel Gorman Cc: Nitin Gupta Cc: Jonathan Corbet Cc: Khalid Aziz Cc: David Rientjes Cc: Vinayak Menon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: UtsavBalar1231 Change-Id: Iba2e253634c373c8724572de3de16029230b0b0e --- Documentation/sysctl/vm.txt | 3 ++- include/linux/compaction.h | 2 ++ include/linux/mmzone.h | 1 + kernel/sysctl.c | 2 +- mm/compaction.c | 38 +++++++++++++++++++++++++++++++++++-- 5 files changed, 42 insertions(+), 4 deletions(-) diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt index f5412f666896..23605260b3f7 100644 --- a/Documentation/sysctl/vm.txt +++ b/Documentation/sysctl/vm.txt @@ -118,7 +118,8 @@ compaction_proactiveness This tunable takes a value in the range [0, 100] with a default value of 20. This tunable determines how aggressively compaction is done in the -background. Setting it to 0 disables proactive compaction. +background. Write of a non zero value to this tunable will immediately +trigger the proactive compaction. Setting it to 0 disables proactive compaction. Note that compaction has a non-trivial system-wide impact as pages belonging to different processes are moved around, which could also lead diff --git a/include/linux/compaction.h b/include/linux/compaction.h index 3297d86d008f..4182d1c93c75 100644 --- a/include/linux/compaction.h +++ b/include/linux/compaction.h @@ -88,6 +88,8 @@ extern int sysctl_compact_memory; extern unsigned int sysctl_compaction_proactiveness; extern int sysctl_compaction_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos); +extern int compaction_proactiveness_sysctl_handler(struct ctl_table *table, + int write, void *buffer, size_t *length, loff_t *ppos); extern int sysctl_extfrag_threshold; extern int sysctl_compact_unevictable_allowed; diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index db51731802b5..69c2a6c8e545 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -916,6 +916,7 @@ typedef struct pglist_data { enum zone_type kcompactd_classzone_idx; wait_queue_head_t kcompactd_wait; struct task_struct *kcompactd; + bool proactive_compact_trigger; #endif /* * This is a per-node reserve of pages that are not available diff --git a/kernel/sysctl.c b/kernel/sysctl.c index ba0da03e1113..841927c71c86 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1830,7 +1830,7 @@ static struct ctl_table vm_table[] = { .data = &sysctl_compaction_proactiveness, .maxlen = sizeof(sysctl_compaction_proactiveness), .mode = 0644, - .proc_handler = proc_dointvec_minmax, + .proc_handler = compaction_proactiveness_sysctl_handler, .extra1 = &zero, .extra2 = &one_hundred, }, diff --git a/mm/compaction.c b/mm/compaction.c index b62334cd0dfc..d88535ff316b 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -2647,6 +2647,30 @@ int sysctl_compact_memory; */ unsigned int __read_mostly sysctl_compaction_proactiveness = 20; +int compaction_proactiveness_sysctl_handler(struct ctl_table *table, int write, + void *buffer, size_t *length, loff_t *ppos) +{ + int rc, nid; + + rc = proc_dointvec_minmax(table, write, buffer, length, ppos); + if (rc) + return rc; + + if (write && sysctl_compaction_proactiveness) { + for_each_online_node(nid) { + pg_data_t *pgdat = NODE_DATA(nid); + + if (pgdat->proactive_compact_trigger) + continue; + + pgdat->proactive_compact_trigger = true; + wake_up_interruptible(&pgdat->kcompactd_wait); + } + } + + return 0; +} + /* * This is the entry point for compacting all nodes via * /proc/sys/vm/compact_memory @@ -2691,7 +2715,8 @@ void compaction_unregister_node(struct node *node) static inline bool kcompactd_work_requested(pg_data_t *pgdat) { - return pgdat->kcompactd_max_order > 0 || kthread_should_stop(); + return pgdat->kcompactd_max_order > 0 || kthread_should_stop() || + pgdat->proactive_compact_trigger; } static bool kcompactd_node_suitable(pg_data_t *pgdat) @@ -2842,9 +2867,16 @@ static int kcompactd(void *p) while (!kthread_should_stop()) { unsigned long pflags; + /* + * Avoid the unnecessary wakeup for proactive compaction + * when it is disabled. + */ + if (!sysctl_compaction_proactiveness) + timeout = MAX_SCHEDULE_TIMEOUT; trace_mm_compaction_kcompactd_sleep(pgdat->node_id); if (wait_event_freezable_timeout(pgdat->kcompactd_wait, - kcompactd_work_requested(pgdat), timeout)) { + kcompactd_work_requested(pgdat), timeout) && + !pgdat->proactive_compact_trigger) { psi_memstall_enter(&pflags); kcompactd_do_work(pgdat); @@ -2879,6 +2911,8 @@ static int kcompactd(void *p) timeout = default_timeout << COMPACT_MAX_DEFER_SHIFT; } + if (unlikely(pgdat->proactive_compact_trigger)) + pgdat->proactive_compact_trigger = false; } return 0;